3 papers
cs.RO2026
WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving
Mingkai Jia, Jiaxin Guo, Zhijian Shu +5
Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction does not necessarily translate in…
cs.CV2026
EponaV2: Driving World Model with Comprehensive Future Reasoning
Jiawei Xu, Zhizhou Zhong, Zhijian Shu +8
Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving relies heavily on expensive man…
cs.CV2025
LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
Zhijian Shu, Cheng Lin, Tao Xie +8
3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for l…